MENU

Inference

Inference
Brain-inspired neuromorphic AI chip accelerates spiking neural networks
Brain-inspired neuromorphic AI chip accelerates spiking neural networks
Technology News |
Fast, energy-efficient, and compact chip enables SNNs to be used directly in edge devices where data is generated.
AMD buys ZT Systems to drive data center AI
AMD buys ZT Systems to drive data center AI
Business news |
Strategic acquisition to enable to accelerate deployment of optimized rack-scale systems for data center AI.
Aetina and Solomon team up to accelerate AI and 3D vision
Aetina and Solomon team up to accelerate AI and 3D vision
Business news |
Partnership to enable organizations to use AI and 3D vision to boost productivity across manufacturing, semiconductor, retail, and other verticals.
SiPearl partners with Samsung for built-in HBM in Rhea

SiPearl partners with Samsung for built-in HBM in Rhea

Business news |
This partnership marks the emergence of a European pioneer in the use of HBM technology for high-performance low-power microprocessor.

Modular open edge platform scales AI applications
Modular open edge platform scales AI applications
Technology News |
The edge-native software platform simplifies development, deployment and management of edge AI applications.
Startup funds inference compute platform for generative AI
Startup funds inference compute platform for generative AI
Technology News |
d-Matrix is changing the cost economics of deploying AI inference with a compute platform purpose-built for LLMs.
VMware and NVIDIA bring generative AI to enterprises
VMware and NVIDIA bring generative AI to enterprises
Business news |
VMware Private AI Foundation with NVIDIA enables enterprises to ready their businesses for generative AI with support for data privacy, security and control.
PCIe card for autonomous mobility
PCIe card for autonomous mobility
New Products |
Pegasus PCIe card paired with the Recogni SDK provides development and deployment flexibility for any autonomous mobility use case.
Software compresses neural networks without loss of accuracy
Software compresses neural networks without loss of accuracy
Technology News |
Software compresses trained neural networks to 5 to 10 percent of their original size, while maintaining their inference accuracy.
Flex Logix announces production availability of AI inference boards
Flex Logix announces production availability of AI inference boards
New Products |
InferX™ X1M AI inference boards deliver high performance and ultra low power in a tiny M.2 form factor for space and power constrained applications.


10s